SkillEvolBench-Team/Skill-Evol-Bench download history

SkillEvolBench-Team/Skill-Evol-Bench is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 5,382 times (58 in the last 7 days), and 10,396 times in total. It ranks #5,372 among datasets by monthly downloads.

SkillEvolBench Dataset SkillEvolBench is a diagnostic benchmark for testing whether LLM agents can convert episodic task experience into reusable procedural skills. It accompanies the paper SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills. This

Open SkillEvolBench-Team/Skill-Evol-Bench on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.